Comparative Expert Evaluation of Multimodal Large Language Models for Pediatric Rash Diagnosis: Clinical Utility, Safety, Information Quality, and Readability
Dilara Lahut, Özlem Erdede, Rabia Gönül Sezer Yamanel · 2026
Read Comparative Expert Evaluation of Multimodal Large Language Models for Pediatric Rash Diagnosis: Clinical Utility, Safety, Information Quality, and Readability by Dilara Lahut, Özlem Erdede, Rabia Gönül Sezer Yamanel (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13605588.txt.
Description
Dilara Lahut, Özlem Erdede, and Rabia Sezer Yamanel published a 2026 study in which pediatricians graded three AI chatbots on diagnosing children's rashes. Multimodal large language models can read both clinical text and images, but their skill with pediatric rashes was untested. Rashes are one of the most common reasons children visit a doctor.
The team prepared fifteen validated case vignettes, each with a short history and an anonymized photograph. Each case went once to ChatGPT, Gemini, and Grok with the same standard prompt. Three pediatricians, blinded to which platform answered, rated all 45 responses for clinical utility, safety, information quality, diagnostic correctness, and readability. Expert grading shows where chatbots can help parents and where they still risk misleading them.
Catalog record
| CREATOR | Dilara Lahut, Özlem Erdede, Rabia Gönül Sezer Yamanel |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |